wait-what
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected in this skill. The skill consists of natural language instructions to modify the agent's communication style.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to use information from a separate
CONTEXT.mdfile, which creates a theoretical attack surface for indirect prompt injection if that file's content is untrusted. - Ingestion points: Reference to
CONTEXT.mdinSKILL.md. - Boundary markers: None present.
- Capability inventory: The skill does not contain any scripts, tool calls, or network operations, limiting the impact of any potential injection.
- Sanitization: None present.
Audit Metadata